
Routing Claude Code Tasks to Local Ollama Models
transcript
show notes
Claude Code lacks native support for pointing subagents at local inference servers, but developers are splitting traffic using two distinct architectural patterns. This discussion explores model-based proxy interception with tools like llm-router alongside explicit delegation via MCP servers like local-vibes and ollama-code-mcp. It examines configuration inheritance caveats, credential exposure within the request path, loop timeouts, and why silent cloud fallbacks can undermine the exact privacy guarantees that drove local delegation in the first place.
Key sources:
• README + `main.go` source, MIT, Go 1.22+ — https://github.com/mstfknn/llm-router
• README, `skills/local-vibes/SKILL.md`, `hooks/nudge.mjs`, `src/agent.ts`, `src/index.ts`, v0.1.0 — https://github.com/OpenSourceWTF/local-vibes
• README, BENCHMARK.md, SECURITY.md, `server.py`, v0.3.0 — https://github.com/HenryLinyy/local-llm-mcp
Episode 6255 — myweirdprompts.com/n/6255 (permanent short link: myweirdprompts.com/929489)





